audio model · whisper · Windows
Can I run Whisper small on AMD Ryzen AI Halo (128GB)?
Yes. Whisper small runs on AMD Ryzen AI Halo (128GB) at fp16 (whisper.cpp) (~0.85 GB of ~96 GB usable).
Runs at fp16 (whisper.cpp) using ~0.85 GB of ~96 GB usable.
- Peak memory
- ~0.85 GB
- Usable on device
- ~96 GB
- Device memory
- 128 GB
- Quant
- fp16 (whisper.cpp)
How to run it
Use whisper.cpp or faster-whisper at fp16 (whisper.cpp). It is light enough to run on CPU; a GPU just makes it faster.
- Type
- Speech to text
- Parameters
- 244M
- Peak memory
- ~0.85 GB at fp16 (whisper.cpp)
- License
- MIT
- Memory
- 128 GB unified
- Usable for weights
- ~96 GB
- Power draw
- ~120 W
- Best runtime
- llama.cpp (Vulkan/ROCm) / LM Studio
You could also run
Run Whisper small on other hardware
FAQ
Can AMD Ryzen AI Halo (128GB) run Whisper small?
Yes. Whisper small runs on AMD Ryzen AI Halo (128GB) at fp16 (whisper.cpp) (~0.85 GB of ~96 GB usable).
How much memory does Whisper small need?
AMD Ryzen AI Halo (128GB) has room to spare. At fp16 (whisper.cpp) the realistic peak is ~0.85 GB of memory.
What do I use to run Whisper small locally?
Whisper small runs in whisper.cpp or faster-whisper (among others). It runs on CPU, so no GPU is required.
Sources
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-08-03. See methodology.